Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 2839
    Prev
    Next
    INDEX
    Explanations

    descriptions of past experiences with TV shows or movies

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1013
    +0.09
    0.3%
    393
    +0.09
    0.2%
    1415
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.09
    0.06
    1415
    +0.09
    0.02
    458
    +0.08
    0.06
    Negative Logits
     regardé
    -0.62
     userEmail
    -0.55
     postData
    -0.53
     purcha
    -0.52
     michelin
    -0.51
     viendra
    -0.50
     constaté
    -0.50
     préfé
    -0.50
     écout
    -0.50
     userModel
    -0.50
    POSITIVE LOGITS
     revival
    1.02
     revived
    0.98
     revive
    0.94
     resurrected
    0.90
     redis
    0.85
     reviving
    0.85
     resurgence
    0.83
     revi
    0.83
     resurrect
    0.82
     resur
    0.80
    Activations Density 0.904%

    No Known Activations